Skip to content

generator and discriminator input shape issue #7

@loveplay1983

Description

@loveplay1983

def build_generator():
model = Sequential()
# Takes in random values and reshapes it to 7x7x128
# Beginnings of a generated image
model.add(Dense(77128, input_dim=128))
model.add(LeakyReLU(0.2))
model.add(Reshape((7,7,128)))

Model: "sequential_5"
Layer (type) Output Shape Param
dense_5 (Dense) (None, 6272) 809088

def build_discriminator():
model = Sequential()
model.add(Conv2D(32, 5, input_shape=(28,28,1)))
model.add(LeakyReLU(.2))
model.add(Dropout(.4))

Model: "sequential_8"
Layer (type) Output Shape Param
conv2d_33 (Conv2D) (None, 24, 24, 32) 832

Based on the summary of both generator and discriminator, the input dim for the generator is 2, and the input dim for the discriminator is 4. However, the codes were defined with input of generator and discriminator both 3 and 3, which ended up with error message. Hence, suggesting to change the code with generator and discriminator input img = generator.predict(np.random.randn(4,128))

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions